DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Design and evaluation of advanced intelligent flight controllers

Milz, Daniel and Looye, Gertjan (2020) Design and evaluation of advanced intelligent flight controllers. In: AIAA Scitech 2020 Forum. AIAA Scitech 2020 Forum, 6-10 Jan 2020, Orlando, FL. doi: 10.2514/6.2020-1846. ISBN 978-162410595-1.

[img] PDF

Official URL: https://arc.aiaa.org/doi/abs/10.2514/6.2020-1846


Reinforcement learning based methods could be feasible of solving adaptive optimal control problems for nonlinear dynamical systems. This work presents a proof of concept for applying reinforcement learning based methods to robust and adaptive flight control tasks. A framework for designing and examining these methods is introduced by means of the open research civil aircraft model (RCAM) and optimality criteria. A state-of-the-art robust flight controller - the incremental nonlinear dynamic inversion (INDI) controller - serves as a reference controller. Two intelligent control methods are introduced and examined. The deep deterministic policy gradient (DDPG) controller is selected as a promising actor critic reinforcement learning method that currently gains much attraction in the field of robotics. In addition, an adaptive version of a proportional-integral-derivative (PID) controller, the PID neural network (PIDNN) controller, is selected as the second method. The results show that all controllers are able to control the aircraft model. Moreover, the PIDNN controller exhibits improved reference tracking if a good initial guess of its weights is available. In turn, the DDPG algorithm is able to control the nonlinear aircraft model while minimizing a multi-objective value function. This work provides insight into the usability of selected intelligent controllers as flight control functions as well as a comparison to state-of-the-art flight control functions.

Item URL in elib:https://elib.dlr.de/139143/
Document Type:Conference or Workshop Item (Speech)
Title:Design and evaluation of advanced intelligent flight controllers
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Milz, DanielDaniel.Milz (at) dlr.deUNSPECIFIED
Looye, GertjanGertjan.Looye (at) dlr.deUNSPECIFIED
Date:5 January 2020
Journal or Publication Title:AIAA Scitech 2020 Forum
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.2514/6.2020-1846
Keywords:Flight Control, Reinforcement Learning, Artificial Intelligence, Machine Learning, INDI
Event Title:AIAA Scitech 2020 Forum
Event Location:Orlando, FL
Event Type:international Conference
Event Dates:6-10 Jan 2020
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Aeronautics
HGF - Program Themes:fixed-wing aircraft
DLR - Research area:Aeronautics
DLR - Program:L AR - Aircraft Research
DLR - Research theme (Project):L - Systems and Cabin (old)
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of System Dynamics and Control > Aircraft System Dynamics
Deposited By: Milz, Daniel
Deposited On:07 Dec 2020 17:46
Last Modified:07 Dec 2020 17:46

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.